Freelancer

Key Skills

Software

Don't disclose

Other

Top Subject Matter

News data collection and ETL pipeline automation

Customer churn modeling with prepared datasets

Sales data cleaning and report generation

Top Data Types

Computer Code Programming

Top Task Types

Data Collection

Freelancer Overview

NewsFlow: Automated ETL Pipeline (Python-based data collection/ETL project). Brings 4+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include GitHub Actions, Don't disclose, and Other. Education includes Bachelor of Commerce, University of Pretoria (2025) and National Senior Certificate, Umtata High School (2024). AI-training focus includes data types such as Computer Code and Programming and labeling workflows including Data Collection, Evaluation, and Rating.

Labeling Experience

Weather Data Fetcher & Reporter (API data collection/ETL automation)

OtherData Collection

Integrated a third-party weather API to fetch real-time weather data and convert API responses into structured reports. Performed ETL-style transformations to standardize the extracted values for analysis readiness. Produced consistent outputs suitable for downstream data processing and visualization. • Retrieved real-time weather data via a third-party API. • Transformed API responses into structured reports. • Applied ETL processes to standardize extracted fields. • Generated outputs for analysis use.

2025 - 2025

Sales Data Cleaner and Report Generator (Python-based data preprocessing/automation)

OtherData Collection

Created a Python tool to clean raw sales data and generate automated reports, improving the quality and consistency of datasets used for analysis. Transformed and validated incoming records to reduce manual processing time and standardize outputs. Produced recurring summaries to support interpretation of sales performance and trends. • Automated cleaning of raw sales datasets. • Generated automated reporting outputs. • Reduced manual processing time for recurring data. • Prepared cleaned data for analysis and trend review.

2025 - 2025

Customer Churn Prediction Model (data preparation and ML training work)

Don't disclose

Built a customer churn prediction model using Logistic and Linear Regression approaches that required preparing labeled training datasets from raw business data. Performed data cleaning and exploratory data analysis to ensure features and target variables were suitable for modeling. Identified and mitigated data leakage to improve the real-world validity of model evaluation metrics. • Cleaned and explored data prior to training. • Addressed data leakage issues in the dataset. • Trained regression models for churn prediction. • Evaluated performance using accuracy-based metrics and tuning.

2025 - 2025

NewsFlow: Automated ETL Pipeline (Python-based data collection/ETL project)

Data Collection

Developed and automated an end-to-end ETL pipeline that collects daily news headlines from multiple sources for structured storage and downstream analysis. Implemented scripted scraping, transformation, and loading into an SQLite database, then scheduled automated execution via continuous workflows. Managed code version control and documentation to support consistent data acquisition and reuse. • Automated daily headline scraping from various news sources. • Structured persistence using an SQLite database. • Scheduled runs using GitHub Actions. • Maintained version control and README documentation via GitHub.

2025 - 2025

Education

Work History